Checked other resources

• This is a feature request, not a bug report or usage question.
• I added a clear and descriptive title that summarizes the feature request.
• I used the GitHub search to find a similar feature request and didn't find it.
• I checked the LangChain documentation and API reference to see if this feature already exists.
• This is not related to the langchain-community package.

Package (Required)

• langchain
• langchain-openai
• langchain-anthropic
• langchain-classic
• langchain-core
• langchain-model-profiles
• langchain-tests
• langchain-text-splitters
• langchain-chroma
• langchain-deepseek
• langchain-exa
• langchain-fireworks
• langchain-groq
• langchain-huggingface
• langchain-mistralai
• langchain-nomic
• langchain-ollama
• langchain-openrouter
• langchain-perplexity
• langchain-qdrant
• langchain-xai
• Other / not sure / general

Feature Description

The @wrap_tool_call decorator is the only one that does not accept a state_schema parameter (unlike before/after_agent/model and wrap_model_call). While the official documentation outlines how to handle state within such middlewares (by returning Command instances), the @wrap_tool_call decorator provides no mechanism for specifying the required schema.

Use Case

I want to implement a middleware that wraps every tool call and enforces updates to the agent state. Additionally, I want to follow current best practices by defining custom state directly within the middleware itself.

Proposed Solution

No response

Alternatives Considered

An alternative would be to use a class, but the resulting inconsistency is a greater concern here. In my opinion, there is no clear reason to exclude this parameter.

Additional Context

No response